Triple
T11409262
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | iPhone 14 Pro |
E270323
|
entity |
| Predicate | videoRecordingMaxResolution |
P41984
|
FINISHED |
| Object | 4K |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: 4K | Statement: [iPhone 14 Pro, videoRecordingMaxResolution, 4K]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: videoRecordingMaxResolution Context triple: [iPhone 14 Pro, videoRecordingMaxResolution, 4K]
-
A.
videoQuality
Indicates the level or standard of clarity, resolution, and overall visual fidelity associated with a given video.
-
B.
maximumVideoLength
Indicates the greatest allowable or supported duration for a video in this context.
-
C.
maximumResolution
Indicates the highest level of detail or fineness at which something (such as an image, display, or measurement) can be represented or processed.
-
D.
supports4KVideoRecording
chosen
Indicates that the subject is capable of recording video at 4K (Ultra HD) resolution.
-
E.
rearCameraMainResolution
Indicates the primary resolution (in megapixels or similar units) of a device’s main rear-facing camera.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d6aaddeaa8819088b30ef7b50598c9 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8014e72748190a01bde2f0105cedb |
completed | April 9, 2026, 7:43 p.m. |
| PD | Predicate disambiguation | batch_69d7e70ffd708190b62a78ebcbce9f78 |
completed | April 9, 2026, 5:51 p.m. |
Created at: April 8, 2026, 9:34 p.m.